Shivam

Karma: −1

Always looking for feedbacks and happy to be corrected.
PhD in Geometric Group Theory >> Postdoc in Machine Learning >> AI safety Research.
White-box techniques to detect deception at LASR labs
Mentoring AI safety projects at BlueDot

(Seemingly) Aligned AI is the most dangerous AI

Shivam22 Apr 2026 19:35 UTC

−6 points

4 comments1 min readLW link

The Projection Problem: Two Pitfalls in AI Safety Research

Shivam3 Feb 2026 21:03 UTC

6 points

2 comments6 min readLW link

Shivam’s Shortform

Shivam9 Mar 2025 15:29 UTC

1 point

1 comment1 min readLW link

The Road to Evil Is Paved with Good Objectives: Framework to Classify and Fix Misalignments.

Shivam30 Jan 2025 2:44 UTC

1 point

0 comments11 min readLW link

Limits of safe and aligned AI

Shivam8 Oct 2024 21:30 UTC

2 points

0 comments4 min readLW link